LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Medchator 2x7b by Technoculture

 »  All LLMs  »  Technoculture  »  Medchator 2x7b   URL Share it on

  6   
  Adaptllm/medicine-chat   Autotrain compatible Dataset:open-llm-leaderboard/d...   Endpoints compatible   Merge   Microsoft/orca-2-7b   Mixtral   Moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Technoculture/Medchator-2x7b 

Medchator 2x7b Benchmarks

ARC: 57.59 vs 96.7 (so35)-40.4%
HellaSwag: 78.14 vs 95.3 (gpt4)-18%
MMLU: 56.13 vs 88.3 (so35)-36.4%
TruthfulQA: 48.77 vs 59 (gpt4)-17.3%
WinoGrande: 75.3 vs 87.5 (gpt4)-13.9%
GSM8K: 32.83 vs 96.4 (so35)-65.9%
LLME Score: 0.15366
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Medchator 2x7b (Technoculture/Medchator-2x7b)
🌟 Advertise your project 🚀

Medchator 2x7b Parameters and Internals

Model Type 
moe, merge
Additional Notes 
Medchator-2x7b is a Mixture of Experts (MoE) model.
LLM NameMedchator 2x7b
Repository 🤗https://huggingface.co/Technoculture/Medchator-2x7b 
Model Size11.1b
Required VRAM22.1 GB
Updated2025-09-20
MaintainerTechnoculture
Model Typemixtral
Model Files  10.0 GB: 1-of-3   10.0 GB: 2-of-3   2.1 GB: 3-of-3
Model ArchitectureMixtralForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.36.2
Tokenizer ClassLlamaTokenizer
Padding Token<s>
Vocabulary Size32003
Torch Data Typefloat32

Best Alternatives to Medchator 2x7b

Best Alternatives
Context / RAM
Downloads
Likes
DevPearl 2x7B16K / 22.3 GB52
Medorca 2x7b4K / 35.6 GB16502
Phi3 4x4b Uninitialized4K / 22.2 GB50
Youri 2x7b Dev4K / 22.1 GB54
Youri 2x7b V0.24K / 22.1 GB51
Medtulu 2x7b2K / 22.1 GB16372
Note: green Score (e.g. "73.2") means that the model is better than Technoculture/Medchator-2x7b.

Rank the Medchator 2x7b Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 51483 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124
  Support LLM Explorer